| Presentation | 2022-03-08 A study on high-intelligibility speech synthesis of dysarthric speakers using voice conversion from normal speech and multi-speaker vocoder Tetsuro Takano, Takashi Nose, Aoi Kanagaki, Satoshi Watanabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this study, we investigated the possibility of generating intelligible synthetic speech by converting the voice of a normal speaker to that of a dysarthric speaker while maintaining the tone of the speaker's voice. Using the fact that a multi-speaker vocoder can produce clear synthetic voice even with a small amount of impaired speaker data, we demonstrated the effectiveness of speech rate conversion to improve voice similarity, pitch augmentation to overcome monotonicity of intonation, and fine tuning to learn with word data. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | dysarthria / voice conversion / multi-speaker vocoder / CycleGAN / HiFi-GAN |
| Paper # | WIT2021-46 |
| Date of Issue | 2022-03-01 (WIT) |
| Conference Information | |
| Committee | WIT / IPSJ-AAC |
|---|---|
| Conference Date | 2022/3/8(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinji Sakou(Nagoya Inst. of Tech.) |
| Vice Chair | Tomohiro Amemiya(Univ. of Tokyo) |
| Secretary | Tomohiro Amemiya(Saitama Industrial Tech. Center) / (Teikyo Univ.) |
| Assistant | Minako Hosono(AIST) / Aki Sugano(Nagoya Univ.) / Tomoyasu Komori(NHK) |
| Paper Information | |
| Registration To | Technical Committee on Well-being Information Technology / Special Interest Group on Assistive & Accessible Computin |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A study on high-intelligibility speech synthesis of dysarthric speakers using voice conversion from normal speech and multi-speaker vocoder |
| Sub Title (in English) | |
| Keyword(1) | dysarthria |
| Keyword(2) | voice conversion |
| Keyword(3) | multi-speaker vocoder |
| Keyword(4) | CycleGAN |
| Keyword(5) | HiFi-GAN |
| 1st Author's Name | Tetsuro Takano |
| 1st Author's Affiliation | Human Techno System Co., Ltd(HTS) |
| 2nd Author's Name | Takashi Nose |
| 2nd Author's Affiliation | Tohoku University(Tohoku Univ.) |
| 3rd Author's Name | Aoi Kanagaki |
| 3rd Author's Affiliation | Tohoku University(Tohoku Univ.) |
| 4th Author's Name | Satoshi Watanabe |
| 4th Author's Affiliation | Human Techno System Co., Ltd(HTS) |
| Date | 2022-03-08 |
| Paper # | WIT2021-46 |
| Volume (vol) | vol.121 |
| Number (no) | WIT-418 |
| Page | pp.pp.18-23(WIT), |
| #Pages | 6 |
| Date of Issue | 2022-03-01 (WIT) |